Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.9426. Min Act: -0.1700
Data Index: 64751 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.8488. Min Act: -0.1700
Data Index: 2020825 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.8488. Min Act: -0.1700
Data Index: 1582776 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.8176. Min Act: -0.1700
Data Index: 1558091 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.7551. Min Act: -0.1700
Data Index: 7212161 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.7238. Min Act: -0.1700
Data Index: 2016218 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.7551. Min Act: -0.1700
Data Index: 7324685 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6613. Min Act: -0.1700
Data Index: 347612 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6926. Min Act: -0.1700
Data Index: 1869310 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6613. Min Act: -0.1700
Data Index: 2852372 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6613. Min Act: -0.1700
Data Index: 8669486 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6613. Min Act: -0.1700
Data Index: 7739251 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6301. Min Act: -0.1700
Data Index: 2125253 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6301. Min Act: -0.1700
Data Index: 5806702 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6301. Min Act: -0.1700
Data Index: 3887499 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6301. Min Act: -0.1700
Data Index: 6648885 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.6301. Min Act: -0.1700
Data Index: 3537174 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.5988. Min Act: -0.1700
Data Index: 7814219 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.5988. Min Act: -0.1700
Data Index: 7931907 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9426. Min Range: -6.9426
Max Act: 6.5676. Min Act: -0.1700
Data Index: 2718253 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19